Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

"This isn't happening," Ben whispered, staring out the window. Just as he was contemplating finally finishing the repairs on his fence, there was a tap at his door. Mrs. Gable, his other neighbor, was there, a wide smile on her face. "Such a sunny spot you have, Ben!" she exclaimed, her voice syrupy sweet. "A little garden would really liven up the space, wouldn't it?"

Ben’s stomach churned. He could feel a sour taste at the back of his throat. He just wanted to be left alone.

He forced a smile, his jaw aching from the effort. He told her he'd consider it. The sunlight seemed to mock him.

Emotion: frustrated

Cluster: Anger / Hostility
PC1 (Valence): -1.56 Negative
PC2 (Disposition): 0.64

Role in Research

This story is one of 1,000 stories generated for the emotion frustrated. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 frustrated stories, after denoising with neutral dialogue baselines, produces the frustrated emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the frustrated vector is projected through the unembedding matrix.

Promoted:
S0.344
P0.302
exasper0.257
aggravated0.254
que0.252
Suppressed:
unfolding-0.242
otre-0.226
latter-0.220
☺️-0.216
soon-0.212